Successor Features for Transfer in Reinforcement Learning

N/A

Successor Features for Transfer in Reinforcement Learning André Barreto, Will Dabney, Rémi Munos, Jonathan J. Hunt, Tom Schaul, Hado van Hasselt, David Silver {andrebarreto,wdabney,munos,jjhunt,schaul,hado,davidsilver}@google.com DeepMind Abstract Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer frame-…

saved by

• David Yan

related reading

• [2606.09758] Difference-Aware Retrieval Policies for Imitation Learningarxiv.org
• [1606.05312] Successor Features for Transfer in Reinforcement Learningarxiv.org
• Flow Matching Policy Gradientsflowreinforce.github.io
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• The Promise of Hierarchical Reinforcement Learningthegradient.pub
• [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org
• Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
• [2103.06326] S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningarxiv.org
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• RL_Notes__final_.pdfjubayer-ibn-hamid.github.io
• 2203.00543arxiv.org
• Contrastive Learning as Goal-Conditioned Reinforcement Learningarxiv.org